import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
import streamlit as st

# Set page title and icon
st.set_page_config(page_title='Fake News Detection', page_icon=":postal_horn:")

# Load the dataset
df = pd.read_csv("fake_or_real_news.csv")

# Train the model
x = np.array(df["title"])
y = np.array(df["label"])
cv = CountVectorizer()
x = cv.fit_transform(x)

xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.2, random_state=42)
model = MultinomialNB()
model.fit(xtrain, ytrain)


st.title('Fake News Detection :postal_horn:')

# Display an image
st.image("https://upload.wikimedia.org/wikipedia/commons/f/f7/The_fin_de_siècle_newspaper_proprietor_%28cropped%29.jpg")

# Input field for user to enter news headline
default_example = "Aliens decided to buy America after Russia Exploded"
news_headline = st.text_input("Enter a news headline:", default_example)

if st.button("Check"):
    # Make prediction
    df_input = cv.transform([news_headline]).toarray()
    prediction = model.predict(df_input)
    
    # Display prediction result
    if prediction[0] == 'FAKE':
        st.error("This news headline is likely FAKE.")
    else:
        st.success("This news headline is likely REAL.")